INDEX

Explanations

terms related to protein domains and binding mechanisms

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rogens

-0.61

 Himo

-0.60

colorPrimary

-0.54

 Vertra

-0.50

 experimented

-0.49

ünstig

-0.49

 responsible

-0.47

quia

-0.47

 experimenta

-0.47

<?>>

-0.47

POSITIVE LOGITS

 resourceCulture

0.96

 pinulongan

0.88

 Exacts

0.79

 nakalista

0.79

 autorytatywna

0.75

 مشين

0.72

 mostrarán

0.71

parsedMessage

0.70

ngdoc

0.69

AutoScaleMode

0.68

Activations Density 0.060%

terms related to protein domains and binding mechanisms

No Comments

No Known Activations